1 /* 2 * Copyright (c) 1989, 1993 3 * The Regents of the University of California. All rights reserved. 4 * 5 * This code is derived from software contributed to Berkeley by 6 * Case Larsen. 7 * 8 * Redistribution and use in source and binary forms, with or without 9 * modification, are permitted provided that the following conditions 10 * are met: 11 * 1. Redistributions of source code must retain the above copyright 12 * notice, this list of conditions and the following disclaimer. 13 * 2. Redistributions in binary form must reproduce the above copyright 14 * notice, this list of conditions and the following disclaimer in the 15 * documentation and/or other materials provided with the distribution. 16 * 3. All advertising materials mentioning features or use of this software 17 * must display the following acknowledgement: 18 * This product includes software developed by the University of 19 * California, Berkeley and its contributors. 20 * 4. Neither the name of the University nor the names of its contributors 21 * may be used to endorse or promote products derived from this software 22 * without specific prior written permission. 23 * 24 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 25 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 26 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 27 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 28 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 29 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 30 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 31 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 32 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 33 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 34 * SUCH DAMAGE. 35 */ 36 37 #ifndef lint 38 static const char copyright[] = 39 "@(#) Copyright (c) 1989, 1993\n\ 40 The Regents of the University of California. All rights reserved.\n"; 41 #endif /* not lint */ 42 43 #ifndef lint 44 #if 0 45 static char sccsid[] = "@(#)uniq.c 8.3 (Berkeley) 5/4/95"; 46 #endif 47 static const char rcsid[] = 48 "$FreeBSD$"; 49 #endif /* not lint */ 50 51 #include <ctype.h> 52 #include <err.h> 53 #include <limits.h> 54 #include <locale.h> 55 #include <stdio.h> 56 #include <stdlib.h> 57 #include <string.h> 58 #include <unistd.h> 59 60 #define MAXLINELEN (LINE_MAX + 1) 61 62 int cflag, dflag, uflag; 63 int numchars, numfields, repeats; 64 65 FILE *file __P((char *, char *)); 66 void show __P((FILE *, char *)); 67 char *skip __P((char *)); 68 void obsolete __P((char *[])); 69 static void usage __P((void)); 70 int stricoll __P((char *, char*)); 71 72 int 73 main (argc, argv) 74 int argc; 75 char *argv[]; 76 { 77 register char *t1, *t2; 78 FILE *ifp, *ofp; 79 int ch; 80 char *prevline, *thisline, *p; 81 int iflag = 0, comp; 82 83 (void) setlocale(LC_CTYPE, ""); 84 85 obsolete(argv); 86 while ((ch = getopt(argc, argv, "-cdif:s:u")) != -1) 87 switch (ch) { 88 case '-': 89 --optind; 90 goto done; 91 case 'c': 92 cflag = 1; 93 break; 94 case 'd': 95 dflag = 1; 96 break; 97 case 'i': 98 iflag = 1; 99 break; 100 case 'f': 101 numfields = strtol(optarg, &p, 10); 102 if (numfields < 0 || *p) 103 errx(1, "illegal field skip value: %s", optarg); 104 break; 105 case 's': 106 numchars = strtol(optarg, &p, 10); 107 if (numchars < 0 || *p) 108 errx(1, "illegal character skip value: %s", optarg); 109 break; 110 case 'u': 111 uflag = 1; 112 break; 113 case '?': 114 default: 115 usage(); 116 } 117 118 done: argc -= optind; 119 argv +=optind; 120 121 /* If no flags are set, default is -d -u. */ 122 if (cflag) { 123 if (dflag || uflag) 124 usage(); 125 } else if (!dflag && !uflag) 126 dflag = uflag = 1; 127 128 switch(argc) { 129 case 0: 130 ifp = stdin; 131 ofp = stdout; 132 break; 133 case 1: 134 ifp = file(argv[0], "r"); 135 ofp = stdout; 136 break; 137 case 2: 138 ifp = file(argv[0], "r"); 139 ofp = file(argv[1], "w"); 140 break; 141 default: 142 usage(); 143 } 144 145 prevline = malloc(MAXLINELEN); 146 thisline = malloc(MAXLINELEN); 147 if (prevline == NULL || thisline == NULL) 148 errx(1, "malloc"); 149 150 if (fgets(prevline, MAXLINELEN, ifp) == NULL) 151 exit(0); 152 153 while (fgets(thisline, MAXLINELEN, ifp)) { 154 /* If requested get the chosen fields + character offsets. */ 155 if (numfields || numchars) { 156 t1 = skip(thisline); 157 t2 = skip(prevline); 158 } else { 159 t1 = thisline; 160 t2 = prevline; 161 } 162 163 /* If different, print; set previous to new value. */ 164 if (iflag) 165 comp = stricoll(t1, t2); 166 else 167 comp = strcoll(t1, t2); 168 169 if (comp) { 170 show(ofp, prevline); 171 t1 = prevline; 172 prevline = thisline; 173 thisline = t1; 174 repeats = 0; 175 } else 176 ++repeats; 177 } 178 show(ofp, prevline); 179 exit(0); 180 } 181 182 /* 183 * show -- 184 * Output a line depending on the flags and number of repetitions 185 * of the line. 186 */ 187 void 188 show(ofp, str) 189 FILE *ofp; 190 char *str; 191 { 192 193 if (cflag && *str) 194 (void)fprintf(ofp, "%4d %s", repeats + 1, str); 195 if ((dflag && repeats) || (uflag && !repeats)) 196 (void)fprintf(ofp, "%s", str); 197 } 198 199 char * 200 skip(str) 201 register char *str; 202 { 203 register int infield, nchars, nfields; 204 205 for (nfields = numfields, infield = 0; nfields && *str; ++str) 206 if (isspace((unsigned char)*str)) { 207 if (infield) { 208 infield = 0; 209 --nfields; 210 } 211 } else if (!infield) 212 infield = 1; 213 for (nchars = numchars; nchars-- && *str; ++str); 214 return(str); 215 } 216 217 FILE * 218 file(name, mode) 219 char *name, *mode; 220 { 221 FILE *fp; 222 223 if ((fp = fopen(name, mode)) == NULL) 224 err(1, "%s", name); 225 return(fp); 226 } 227 228 void 229 obsolete(argv) 230 char *argv[]; 231 { 232 int len; 233 char *ap, *p, *start; 234 235 while ((ap = *++argv)) { 236 /* Return if "--" or not an option of any form. */ 237 if (ap[0] != '-') { 238 if (ap[0] != '+') 239 return; 240 } else if (ap[1] == '-') 241 return; 242 if (!isdigit((unsigned char)ap[1])) 243 continue; 244 /* 245 * Digit signifies an old-style option. Malloc space for dash, 246 * new option and argument. 247 */ 248 len = strlen(ap); 249 if ((start = p = malloc(len + 3)) == NULL) 250 errx(1, "malloc"); 251 *p++ = '-'; 252 *p++ = ap[0] == '+' ? 's' : 'f'; 253 (void)strcpy(p, ap + 1); 254 *argv = start; 255 } 256 } 257 258 static void 259 usage() 260 { 261 (void)fprintf(stderr, 262 "usage: uniq [-c | -du | -i] [-f fields] [-s chars] [input [output]]\n"); 263 exit(1); 264 } 265 266 int 267 stricoll(s1, s2) 268 char *s1, *s2; 269 { 270 char *p, line1[MAXLINELEN], line2[MAXLINELEN]; 271 272 for (p = line1; *s1; s1++) 273 *p++ = tolower((unsigned char)*s1); 274 *p = '\0'; 275 for (p = line2; *s2; s2++) 276 *p++ = tolower((unsigned char)*s2); 277 *p = '\0'; 278 return strcoll(s1, s2); 279 } 280